Past, ongoing and open student projects are summarized under this link.
Scientific Publications
PhD Thesis
A spike based learning rule and its implementation in analog
hardware, PhD thesis, ETH Zürich, Switzerland, 2000, pdf
Book Chapters
Spike based normalizing Hebbian learning in an analog VLSI artificial neuron P. Häfliger and M. Mahowald, in 'Learning in Silicon', editor: Gert Cauwenberghs, Kluwer Academics, 1999 abstract, pdf
Weight vector normalization in an analog VLSI artificial neuron using a backpropagating action potential P. Häfliger and M. Mahowald, in Neuromorphic Systems, Engineering Silicon from Neurobiology, editors L. S. Smith and A. Hamilton, 1998 abstract, pdf, ps
Journal Articles
A gate leakage feedback element in an adaptive amplifier application H. K. O. Berge and P. Häfliger, IEEE Transactions on Circuits and Systems II, accepted for publication
Adaptive WTA with an analog VLSI neuromorphic learning chip, P. Häfliger, IEEE Transactions on Neural Networks, 2007, vol. 18 (2), p 551-572, IEEE Xplore pdf.
Exploiting Gate Leakage in Sub-Micrometer CMOS for Input Offset Adaptation P. Häfliger and H. K. O. Berge, IEEE Transactions on Circuits and Systems II, 2007, vol. 54 (2), p 127-130, IEEE Xplore pdf.
An Asynchronous 4-to-4 AER Mapper H. Kolle Riis and P. Häfliger, Lecture Notes in Computer Science 3512, 2005 abstract, pdf.
A rank encoder: Adaptive analog to digital conversion exploiting time domain spike signal processing P. Häfliger and E. Jørgensen Aasebø, 'Analog Integrated Circuits and Signal Processing', Kluwer academic publishers, vol. 40, no. 1, p. 39-52, 2004), pdf
Spike based normalizing Hebbian learning in an analog VLSI artificial neuron P. Häfliger and M. Mahowald, 'Analog Integrated Circuits and Signal Processing 18: Special issue on Learning in Silicon', Kluwer Academic Publishers, 1999 abstract, pdf
Peer Reviewed Conference Papers
High-Speed Serial AER on FPGA H. K. O. Berge and P. Häfliger, ISCAS 2007, New orleans, USA, pdf.
AER Building Blocks for Multi-Layer Multi-Chip Neuromorphic Vision Systems R. Serrano-Gotarredona, M. Oster, P. Lichtsteiner, A. Linares-Barranco, R. Paz-Vicente, F. Gómez-Rodríguez, H. Kolle Riis, T. Delbrück, S. C. Liu, S. Zahnd, A. M. Whatley, R. Douglas, P. Häfliger, G. Jimenez-Moreno, A. Civit, T. Serrano-Gotarredona, A. Acosta-Jiménez, B. Linares-Barranco, Advances in Neural Information Processing Systems (NIPS), vol. 18, 2005 abstract, pdf.
A Foveated AER Imager Chip M. Azadmehr and J. P. Abrahamsen, and P. Häfliger, Conference paper at ISCAS 2005 in Kobe abstract, pdf.
A Time Domain Winner-Take-All network of Integrate-and-Fire Neurons J. P. Abrahamsen, P. Häfliger, and T. S. Lande, Conference paper ISCAS 2004 in Vancouver abstract, pdf
Spike Based Learning with Weak Multi-Level Static Memory H. Kolle Riis and P. Häfliger, conference paper ISCAS 2004 in Vancouver abstract, pdf
A Multi-Level Static Memory Cell P. Häfliger and H. Kolle Riis, Conference paper ISCAS 2003 in Bangkok abstract, pdf
An integrated circuit computing shift in stereo pictures using time domain spike signals P. Häfliger and F. Bergh, Conference paper NORCHIP 2002 in Københaven abstract, pdf
Asynchronous event redirecting in bio-inspired communication P. Häfliger, conference paper ICECS 2001 in Malta abstract, pdf
Learning a temporal code P. Häfliger, conference paper ESANN 99 in Brügge abstract, pdf, ps
Floating gate analog memory for parameter and variable storage in a learning silicon neuron P. Häfliger and C. rasche, conference paper ISCAS'99 abstract, pdf, ps
A spike based learning neuron in analog VLSI P. Häfliger and M. Mahowald and L. Watts, conference Paper NIPS 96 abstract , pdf, ps
Prompt Radio Emission of Supernovae: Plasma Radiation Alternative? (A. O. Benz and P. D. Haefliger, 95) Radio emissions from the stars and the sun (Editors: J.M. Paredes and A.R. Taylor) Astron. Soc. Pac. Conf., Vol. 93 S. 96
Others
On using the time domain for analog signal representation in electronic circuits P. Häfliger, Newsletter: The Neuromorphic Engineer, Vol. 1, No. 1, 2004
Learning through search (my master project)
I have programmed a Backgammon game that learns playing on its own, using the 'learning by search' algorithm that differs from the more popular TD(lambda)-algorithm.
You can
download the documentation of the project but be aware that it is written in German.
Playing against my master thesis
Here it was for a while possible to play against my diploma thesis through a java applet ;-) For the moment, though, I stopped updating the server software for the newest opperating system. If someone is really interested, please get in touch with me.
Address
Philipp Häfliger
Insitute of Informatics
University of Oslo
PO Box 1080, Blindern
N-0316 Oslo
Norway
Tel: +47 22 84 01 18
Fax: +47 22 85 24 01
WARNING: Since spam is overflowing in my mailbox nowadays, I apply a quite rigorous mail filter. If you try to approach me for the first time by e-mail, I may never see it. It is best to call or write to me.
